Hugging Face's logo

dtorber
/
bert-base-cased

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
Metrics Community
dtorber commited on
Commit
ba88731
·
verified ·
1 Parent(s): 85f1df9

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. README.md +23 -19
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/May16_18-59-34_tardis/events.out.tfevents.1715882775.tardis.5553.0 +3 -0
  5. training_args.bin +2 -2
README.md CHANGED
@@ -18,14 +18,15 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.4624
22
- - F1 Macro: 0.9016
23
- - F1: 0.9343
24
- - F1 Neg: 0.8689
25
- - Acc: 0.9125
26
- - Prec: 0.9432
27
- - Recall: 0.9257
28
- - Mcc: 0.8036
 
29
 
30
  ## Model description
31
 
@@ -48,25 +49,28 @@ The following hyperparameters were used during training:
48
  - train_batch_size: 8
49
  - eval_batch_size: 8
50
  - seed: 42
 
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
- - num_epochs: 5
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc |
59
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
60
- | No log | 1.0 | 474 | 0.3773 | 0.8286 | 0.8676 | 0.7896 | 0.8375 | 0.9064 | 0.8320 | 0.6623 |
61
- | 0.4662 | 2.0 | 948 | 0.4197 | 0.8638 | 0.9070 | 0.8205 | 0.8775 | 0.8819 | 0.9336 | 0.7305 |
62
- | 0.3045 | 3.0 | 1422 | 0.4950 | 0.8808 | 0.9219 | 0.8397 | 0.895 | 0.8794 | 0.9688 | 0.7711 |
63
- | 0.2105 | 4.0 | 1896 | 0.4999 | 0.8817 | 0.9175 | 0.8459 | 0.8925 | 0.9019 | 0.9336 | 0.7644 |
64
- | 0.1246 | 5.0 | 2370 | 0.5317 | 0.8889 | 0.9198 | 0.8581 | 0.8975 | 0.9216 | 0.9180 | 0.7779 |
 
 
65
 
66
 
67
  ### Framework versions
68
 
69
- - Transformers 4.40.1
70
- - Pytorch 2.3.0+cu121
71
  - Datasets 2.18.0
72
- - Tokenizers 0.19.1
 
18
 
19
  This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.8345
22
+ - F1 Macro: 0.9216
23
+ - F1: 0.9508
24
+ - F1 Neg: 0.8924
25
+ - Acc: 0.9325
26
+ - Prec: 0.9321
27
+ - Recall: 0.9703
28
+ - Mcc: 0.8451
29
+ - Millor Epoca: 5
30
 
31
  ## Model description
32
 
 
49
  - train_batch_size: 8
50
  - eval_batch_size: 8
51
  - seed: 42
52
+ - distributed_type: multi-GPU
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: linear
55
+ - num_epochs: 7
56
  - mixed_precision_training: Native AMP
57
 
58
  ### Training results
59
 
60
+ | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc | Millor Epoca |
61
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|:------------:|
62
+ | 0.2657 | 1.0 | 1698 | 0.3480 | 0.9031 | 0.9370 | 0.8692 | 0.915 | 0.9336 | 0.9405 | 0.8063 | 1 |
63
+ | 0.0983 | 2.0 | 3396 | 0.5281 | 0.9039 | 0.9366 | 0.8712 | 0.915 | 0.9401 | 0.9331 | 0.8078 | 2 |
64
+ | 0.043 | 3.0 | 5094 | 0.5741 | 0.9016 | 0.9343 | 0.8689 | 0.9125 | 0.9432 | 0.9257 | 0.8036 | 2 |
65
+ | 0.0239 | 4.0 | 6792 | 0.8465 | 0.9115 | 0.9460 | 0.8770 | 0.925 | 0.9164 | 0.9777 | 0.8282 | 4 |
66
+ | 0.0134 | 5.0 | 8490 | 0.8345 | 0.9216 | 0.9508 | 0.8924 | 0.9325 | 0.9321 | 0.9703 | 0.8451 | 5 |
67
+ | 0.0104 | 6.0 | 10188 | 0.9451 | 0.9108 | 0.9431 | 0.8784 | 0.9225 | 0.9312 | 0.9554 | 0.8223 | 5 |
68
+ | 0.0 | 7.0 | 11886 | 0.9742 | 0.9081 | 0.9412 | 0.875 | 0.92 | 0.9309 | 0.9517 | 0.8167 | 5 |
69
 
70
 
71
  ### Framework versions
72
 
73
+ - Transformers 4.38.2
74
+ - Pytorch 2.2.1+cu121
75
  - Datasets 2.18.0
76
+ - Tokenizers 0.15.2
config.json CHANGED
@@ -28,7 +28,7 @@
28
  "position_embedding_type": "absolute",
29
  "problem_type": "single_label_classification",
30
  "torch_dtype": "float32",
31
- "transformers_version": "4.40.1",
32
  "type_vocab_size": 2,
33
  "use_cache": true,
34
  "vocab_size": 28996
 
28
  "position_embedding_type": "absolute",
29
  "problem_type": "single_label_classification",
30
  "torch_dtype": "float32",
31
+ "transformers_version": "4.38.2",
32
  "type_vocab_size": 2,
33
  "use_cache": true,
34
  "vocab_size": 28996
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52ef99193379bb66736f9fcde55f4e1c9cd90617c97c3cfb5253840e95230067
3
  size 433270768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e0b9d9421b6a0b14b0c068edbaabceffff3b3bcd750771ff210bf3cedf82f9f
3
  size 433270768
runs/May16_18-59-34_tardis/events.out.tfevents.1715882775.tardis.5553.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0034ae88429085d79aaff3933cebb963e5ce47c3f1fc0df3b0cd55f06f067b0
3
+ size 6416
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1d1296427c77341cc74b24d166737e59dfaf8a0d16b9a420f916fc6aea03841
3
- size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3a427e58d86f0dfca403b8841b461deb6177fc29e874c66654c576085c23201
3
+ size 5112